Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning

ArXi:2602.02098v2 Announce Type: replace-cross Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide formal performance guarantees, which are indispensable when deploying policies in safety-critical settings. We present an approach for computing high-confidence guarantees on the performance of a multi-task policy on tasks not seen during